Skip to main content
Nous Research’s Hermes Agent is an open-source AI agent designed to improve itself over time. It comes with memory that persists across sessions, a built-in learning loop, more than 40 integrated tools, and support for multiple platforms, including CLI, Telegram, Discord, Slack, and WhatsApp.

​
Prerequisites

  • A Kimi API key from the Kimi Platform
  • macOS, Linux, or Windows (WSL2 only; native Windows is not supported)

​
Set up the Kimi API in Hermes Agent

​
Step 1: Install Hermes Agent

Run the one-line installer in your terminal: 
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
The script automatically detects and installs missing dependencies, sets up a virtual environment, and registers the global hermes command. Install Hermes Agent

​
Step 2: Choose Kimi as your model provider

During the initial setup, you will be prompted to choose a model provider. Select Kimi/Moonshot from the list, then set kimi-k2.6 as your default model. Select Kimi as provider Select Kimi K2.6 as the default model

​
Step 3: Set up Kimi API in Hermes Agent

  1. Sign in to the Kimi Platform and top up your account. A $5 deposit includes a $5 bonus; a $20+ deposit unlocks Tier 2, providing lower latency and higher stability for complex multi-step tasks.
Charge for Kimi API
  1. Navigate to API Keys, click Create API Key, and save it in a secure location.
Create a Kimi API key
  1. Return to your terminal and enter your Kimi API key when prompted.
Enter Kimi API Key

​
Step 4: Start chatting with Hermes Agent

After completing the configuration, launch the agent by typing hermes in your terminal to start your first session. Chat with Hermes

​
Troubleshooting Hermes Agent

When integrating Hermes Agent with a model provider, you may occasionally run into errors. Most errors come from misconfigured API keys, incorrect model identifiers, or provider-specific limitations. Below are the most common issues and how to fix them.

​
/model only shows one provider / can’t switch providers

  • Cause: The /model command (used within a chat session) only allows you to switch between providers that have already been configured.
  • Solution: Exit the current session, then run hermes model in your terminal to add additional providers.
# Exit the Hermes chat session first (Ctrl+C or /quit)
# Run the full provider setup wizard
hermes model
# This lets you: add providers, run OAuth, enter API keys, configure endpoints

​
API key not working

  • Cause: The API key is missing, expired, incorrectly configured, or associated with the wrong provider.
  • Solution:
# Check your configuration
hermes config show
# Re-configure your provider
hermes model
# Or set directly
hermes config set MOONSHOT_API_KEY sk-xxxxxxxxxxxx

​
Model not available / model not found

  • Cause: The specified model identifier is invalid or unsupported by your provider.
  • Solution:
# List available models for your provider
hermes model
# Set a valid model
hermes config set HERMES_MODEL moonshot/kimi-k2.6

​
Rate limiting (429 errors)

  • Cause: You’ve hit the rate limits set by your provider.
  • Solution: Wait briefly and try again. For more consistent usage, consider upgrading your provider plan, switching to a different model or provider, or using hermes chat --provider <alternative> to route requests to another backend.